unslothai/unsloth v0.1.905-beta: Sandboxing is here!
We're introducing Windows, Mac and Linux sandboxing in Unsloth!
ProofCode ↗
Key points
- Turn any text or vision LLM into a Jev-style decision model in Unsloth, with decision accuracy going from 30% to 80%.
- Train, test, export and serve decision models directly from Unsloth.
- Load ComfyUI diffusion models natively in Unsloth
- Unsloth now recognises ComfyUI checkpoints and local model folders automatically.
Sources (1)
- [1]unslothai/unsloth v0.1.905-beta: Sandboxing is here!GitHub: unslothai/unsloth · Oct 8, 03:43 PM
We're introducing Windows, Mac and Linux sandboxing in Unsloth!
Turn any text or vision LLM into a Jev-style decision model in Unsloth, with decision accuracy going from 30% to 80%.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards
- Oct 8, 2026ConwayResearch/Underdog-Saluki-27B-1.0
- Oct 8, 2026The model that didn't exist, so you made it yourself
- Oct 7, 2026unslothai/unsloth v0.1.904-beta: Train your own Decision model
- Oct 7, 2026Introducing Falcon ASR
- Oct 7, 2026Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning